If there’s interest, I’m happy to include a few here (including some from fellow LessWrong users):
Review by The Wall Street Journal
Review by Owain Evans (Owain_Evans)
Related: Goodreads – The Alignment Problem: Machine Learning and Human Values
The book 'The Alignment Problem' was published on October 6th, 2020.
Brian Christian posted on Facebook:
TODAY IS THE DAY!
After four years, a hundred interviews, 4,528 git commits, 1,057 references, 9,900 copyedits, and thirty hours in a recording studio, today THE ALIGNMENT PROBLEM finally enters the world.
The twin questions of ethics and safety in AI (more precisely, machine-learning) systems are, in my view, going to be the defining issues of the decade and perhaps the century. We are essentially (and in some cases literally) putting the world on a kind of autopilot, from our highways to our courthouses. There are many reasons to worry whether our fuzzy human intentions and sharp machine objectives, in fact, match.
Fortunately there is an incredibly vigorous movement rising to meet that challenge head-on, and it comprises some of the smartest and kindest people I've had the privilege to call colleagues and friends.
I've tried to tell the story of that harrowing and urgent challenge, our dynamic and exuberant response, the progress made and the problems remaining, and what it ultimately tells us about ourselves.
I hope you'll read, or listen, and can't wait to hear what you think.